fetchFull detail for one project id returned by search (the ChatGPT fetch contract): a text summary, the opening URL and metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | ||
| url | Yes | Absolute https URL the user can open | |
| text | Yes | ||
| title | Yes | ||
| metadata | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Output schema / $schemaPrevious value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds useful output details—text summary, opening URL, metadata—without contradicting annotations. It does not discuss errors or rate limits, but for a simple read operation with strong annotation coverage this is sufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single well-structured sentence that front-loads the core behavior and then lists the returned contents. No words are wasted, and the structure is easy for an agent to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter fetch operation with full annotations and an output schema, the description is complete. It states what the tool returns, how to source the id, and relies on annotations for safety behavior; nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, but the description compensates by clarifying that the id is 'one project id returned by search.' Since there is only one parameter and the schema enforces UUID format, this added context is enough to make the parameter meaningful.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool fetches full detail for a single project id, including summary, opening URL, and metadata. It is a specific verb + resource, but it does not explicitly differentiate from the sibling get_project tool, so it falls short of full sibling-level distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The phrase 'returned by search' gives clear context that this tool is meant for ids obtained from search results. However, it does not provide exclusions or directly name alternatives, so the guidance is contextual rather than fully explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resources, but several overlapping pairs exist: search/list_projects both find projects by title, fetch/get_project both return project details, and upload_logo_image/request_logo_image_upload are two upload paths. The descriptions help clarify boundaries, but an agent could still misselect.
Tool names overwhelmingly follow a clear verb_noun snake_case pattern (create_, list_, get_, update_, delete_). Minor deviations like bare 'fetch' and 'search', plus the mixed '3d' in generate_3d_model vs '3D' in descriptions, keep it from being perfectly consistent.
At 31 tools, this exceeds the 25+ threshold where agent tool selection becomes cognitively heavy. While the server covers a broad platform, several tools are near-redundant and could be consolidated, making the count feel inflated.
The surface covers project lifecycle, sharing/publishing, AI generation, uploads, materials, and account/plan management quite thoroughly. Minor gaps exist, such as no direct create_coin_project tool and no deletion for generation runs, but these are workable.